Reconstruction of People in Loose Clothing
This addresses the problem of accurately modeling clothed humans in 3D from single images, which is important for applications in computer vision, but it is incremental as it builds on existing parametric and non-parametric approaches.
The paper tackles 3D human body reconstruction from monocular images for people in loose clothing, proposing SHARP, an end-to-end network that recovers detailed geometry and appearance, achieving superior performance on Cloth3D and THuman datasets compared to state-of-the-art methods.
3D human body reconstruction from monocular images is an interesting and ill-posed problem in computer vision with wider applications in multiple domains. In this paper, we propose SHARP, a novel end-to-end trainable network that accurately recovers the detailed geometry and appearance of 3D people in loose clothing from a monocular image. We propose a sparse and efficient fusion of a parametric body prior with a non-parametric peeled depth map representation of clothed models. The parametric body prior constraints our model in two ways: first, the network retains geometrically consistent body parts that are not occluded by clothing, and second, it provides a body shape context that improves prediction of the peeled depth maps. This enables SHARP to recover fine-grained 3D geometrical details with just L1 losses on the 2D maps, given an input image. We evaluate SHARP on publicly available Cloth3D and THuman datasets and report superior performance to state-of-the-art approaches.